Your Own AI Infrastructure: Building a Complete Local AI Stack

In this talk, we’ll walk through building a complete, self-hosted AI infrastructure stack from the ground up. You’ll learn how to select the right foundation model for your use case, choose an appropriate inference backend, orchestrate multiple models with an inference orchestrator, and expose everything through an API gateway. We’ll then demonstrate how to leverage this local AI stack to power real applications: a self-hosted chat interface (OpenWebUI), a coding agent (OpenCode), and a personal assistant (OpenClaw).

This is for anyone who wants to break free from cloud AI dependencies, maintain data privacy, reduce costs, and have full control over their AI infrastructure.